A General Approach to Dropout in Quantum Neural Networks

Abstract

In classical Machine Learning, "overfitting" is the phenomenon occurring when a given model learns the training data excessively well, and it thus performs poorly on unseen data. A commonly employed technique in Machine Learning is the so called "dropout", which prevents computational units from becoming too specialized, hence reducing the risk of overfitting. With the advent of Quantum Neural Networks as learning models, overfitting might soon become an issue, owing to the increasing depth of quantum circuits as well as multiple embedding of classical features, which are employed to give the computational nonlinearity. Here we present a generalized approach to apply the dropout technique in Quantum Neural Network models, defining and analysing different quantum dropout strategies to avoid overfitting and achieve a high level of generalization. Our study allows to envision the power of quantum dropout in enabling generalization, providing useful guidelines on determining the maximal dropout probability for a given model, based on overparametrization theory. It also highlights how quantum dropout does not impact the features of the Quantum Neural Networks model, such as expressibility and entanglement. All these conclusions are supported by extensive numerical simulations, and may pave the way to efficiently employing deep Quantum Machine Learning models based on state-of-the-art Quantum Neural Networks.

References in corpus (33)

• Adam: A Method for Stochastic Optimization
• Quantum Computing in the NISQ era and beyond
• Quantum Machine Learning
• A variational eigenvalue solver on a quantum processor
• Variational Quantum Algorithms
• Entanglement detection
• Barren plateaus in quantum neural network training landscapes
• Noisy intermediate-scale quantum (NISQ) algorithms
• Circuit-centric quantum classifiers
• Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Data re-uploading for a universal quantum classifier
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Quantum advantage in learning from experiments
• Experimental Comparison of Two Quantum Computing Architectures
• Generalization in quantum machine learning from few training data
• Quantum Natural Gradient
• Effect of barren plateaus on gradient-free optimization
• Theory of overparametrization in quantum neural networks
• Generalization in Quantum Machine Learning: a Quantum Information Perspective
• Quantum Machine Learning for Chemistry and Physics
• Equivalence of quantum barren plateaus to cost concentration and narrow gorges
• Entanglement Devised Barren Plateau Mitigation
• Quantum computing models for artificial neural networks
• Understanding quantum machine learning also requires rethinking generalization
• A Universal Training Algorithm for Quantum Deep Learning
• Generalization despite overfitting in quantum machine learning models
• Variational learning for quantum artificial neural networks
• On the natural gradient for variational quantum eigensolver
• Overfitting in quantum machine learning and entangling dropout
• Entanglement entropy production in Quantum Neural Networks
• Quantum Dropout: On and Over the Hardness of Quantum Approximate Optimization Algorithm
• Quantum variational learning for entanglement witnessing

Cited by in corpus (8)

• Quantum Latent Diffusion Models
• LEP-QNN: Loan Eligibility Prediction using Quantum Neural Networks
• A Post-Training Approach for Mitigating Overfitting in Quantum Convolutional Neural Networks
• Quantum Circuit Design using a Progressive Widening Enhanced Monte Carlo Tree Search
• Permutation-equivariant quantum convolutional neural networks
• Benchmarking of quantum fidelity kernels for Gaussian process regression
• Double descent in quantum kernel methods
• Introducing Reduced-Width QNNs, an AI-inspired Ansatz Design Pattern